Please wait a minute...
浙江大学学报(工学版)
J4  2014, Vol. 48 Issue (2): 292-296    DOI: 10.3785/j.issn.1008-973X.2014.02.016
电信技术     
一种嵌入式汽车鸟瞰全景图拼接算法
杨力, 朱株, 刘济林
浙江大学 信息与电子工程学系,浙江 杭州 310027
Bird’s-eye panoramic view algorithm for vehicle’s embedded system
YANG Li, ZHU Zhu, LIU Ji-lin
Department of Information Science and Electronic Engineering, Zhejiang University, Hangzhou 310027, China
 全文: PDF(1401 KB)   HTML
摘要：

为了解决汽车周围360°场景重建问题，提出一种适用于车载嵌入式平台的鸟瞰全景图拼接算法，可作为智能汽车环境感知的有效手段.将4个鱼眼摄像头安装于汽车车身，可获得近距离道路环境的图像；采用一种鱼眼图像投影到地面的方法，克服传统方法中存在盲区的问题，同时大大提高计算速度；提出一种基于时域和空域信息的图像融合方法，可以解决摄像机位置差异给拼接造成的困难；为了解决摄像机快速标定问题，采用一种交互式姿态调整方法，运算过程简单，对摄像机安装角度没有精确要求.结果表明，该算法能够实时生成高质量的全景图.
Abstract:

A panoramic image stitching algorithm for embedded system was proposed to  reconstruct the 360-degree scene for intelligent vehicles. We used four fish-eye cameras to acquire the images of the near road area. A method of mapping the fish-eye image to the bird's-eye view  eliminated the blind spots of the driver with low computational complexity. An image fusion method solved the parallax problem in image stitching by combining time and space-domain information. For convenience of installation and calibration of the cameras, an interactive tunning process was proposed to simplify the installation and make the calibration of extrinsic parameters easy. The experiment results indicate that the proposed method can produce panoramic image with high quality.
出版日期: 2014-02-01
:  TN 911  
基金资助:

国家自然科学基金资助项目（60534070，90820306）.
通讯作者: 刘济林，男，教授、博导.     E-mail: liujl@zju.edu.cn
作者简介: 杨力（1979—），男，湖北人，博士生，主要从事机器视觉研究.E-mail: larryy@zju.edu.cn
服务　　
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章　　

引用本文:

杨力, 朱株, 刘济林. 一种嵌入式汽车鸟瞰全景图拼接算法[J]. J4, 2014, 48(2): 292-296.

YANG Li, ZHU Zhu, LIU Ji-lin. Bird’s-eye panoramic view algorithm for vehicle’s embedded system. J4, 2014, 48(2): 292-296.

链接本文:

http://www.zjujournals.com/eng/CN/10.3785/j.issn.1008-973X.2014.02.016    或    http://www.zjujournals.com/eng/CN/Y2014/V48/I2/292

［1］ RICHARD S. Image alignment and stitching: a tutorial ［J］. Foundations and Trends in Computer Graphics and Vision archive, 2006,2(1): 1104.
［2］ LIU Yu-chih, LIN Kai-ying. Bird’s-eye view vision system for vehicle surrounding monitoring \
[C\]∥ Robvis’08 Proceedings Of The 2nd International Conference On Robot Vision. Heidelberg: Springer-Verlag Berlin, 2008: 207-218.
［3］ YEBES J J, ALCANTARILLA P F. Surrounding view for enhancing safety on vehicles［C］∥ IEEE Intelligent Vehicles Symposium, Proceedings of Workshop Perception in Robotics. Spain: \
[s. n.\], 2012: 596-601.
［4］ SHI Gang-Li, YING Hai. Easy calibration of a blind-spot-free fisheye camera system using a scene of a parking space ［J］. IEEE Transactions on Intelligent Transportation Systems, 2011, 12( 1): 232-242.
［5］ EHLGEN T, PAJDLA T. AMMON D. Eliminating blind spots for assisted driving ［J］. IEEE Transactions on Intelligent Transportation Systems, 2008, 9: 657-665.
［6］ CHEN Y Y, TU Y Y. An embedded system for vehicle surrounding monitoring ［C］∥ International Conference on Power Electronics and Intelligent Transportation System. Shenzhen: \
[s.n.\], 2009: 92-95.
［7］ HARTLEY R, ZISSERMAN A. Multiple view geometry in computer vision ［M］.
Cambridge: Cambridge University Press,  2000: 325-340.
［8］ BOUGUET J V. Camera calibration toolbox for matlab ［EB/OL］. 2012-12-08. http:∥www.vision.caltech.edu/bouguetj/calib_doc
［9］ SRIKANTHA A, SIDIB E D. Ghost detection and removal for high dynamic range images: Recent advances ［J］. Signal Processing: Image Communication, 2012, 27( 6): 650-662.
［10］ UYTTENDAELE M, EDEN A. Eliminating ghosting and exposure artifacts in image mosaics ［C］∥ IEEE Conference on Computer Vision and Pattern Recognition. Kauai. Hawaii: \
[s. n.\], 2001: 10636919.
[1] 项楠, 赵航芳, 宫先仪. 非寻复域状态-空间滤波[J]. J4, 2014, 48(4): 727-733.
[2] 张文斌, 杨辰龙, 周晓军. 形态滤波方法在振动信号降噪中的应用[J]. J4, 2009, 43(11): 2096-2099.